© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87412
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Creek" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑģÑĮ
    -0.07
    iphery
    -0.07
    omi
    -0.06
    tras
    -0.06
    ique
    -0.06
    tra
    -0.06
    igue
    -0.06
    ÑĤ
    -0.06
    cy
    -0.06
     conn
    -0.06
    POSITIVE LOGITS
    oven
    0.08
    çķ
    0.08
     Baldwin
    0.08
    ery
    0.08
    خاÙĨÙĩ
    0.07
    ertest
    0.07
    ollow
    0.07
    ereum
    0.07
    .Collectors
    0.07
    esh
    0.07
    Activations Density 0.004%

    No Known Activations